Ingénierie des systèmes d information

Journal Information
ISSN / EISSN : 1633-1311 / 2116-7125
Total articles ≅ 754
Current Coverage

Latest articles in this journal

, Manchala Sadanandam
Ingénierie des systèmes d information, Volume 26, pp 275-283;

Telugu language is one of the historical languages and belongs to the Dravidian family. It contains three dialects named Telangana, Costa Andhra, and Rayalaseema. This paper identifies the dialects of the Telugu language. MFCC, Delta MFCC, and Delta-Delta MFCC are applied with 39 feature vectors for the dialect identification. In addition, ZCR is also applied to identify the dialects. At last combined all the MFCC and ZCR features. A standard database is created to identify the dialects of the Telugu language. Different statistical methods like HMM and GMM are applied for the classification purpose. To improve the accuracy of the model, dimensionality reduction technique PCA is applied to reduce the number of features extracted from the speech signal and applied to models. In this work, with the application of dimensionality reduction, there is an increase in the accuracy of models observed.
Khoirul Anam, Beni Asyhar, Kundharu Saddhono, Bagus Wahyu Setyawan
Ingénierie des systèmes d information, Volume 26, pp 265-273;

The development of internet and information technology made a system to the practical, effective, and efficient. One of the impacts is ease to make scheduling information system in university. This research is research and development (R&D) models which have aim to develop the website-based scheduling information system to increase the effectivity of lecturer’s performance and learning process in IAIN Tulungagung. E-SIP program develop by using software development life cycle in term of waterfall model. Waterfall model was selected because it was easy and efficient. This system development consisted of system need analysis, system design, implementation, testing, dissemination, and maintenance. Data collecting system using literature review, field study, and interview. Furthermore, data also collected from questionnaire scores of E-SIP validations conducted by the validator and respondents, in terms of admins. After doing some development phase and trial, the E-SIP was developed and ready to use to make scheduling process in IAIN Tulungagung. E-SIP possibly runs with using any browser supporting the java-script system. The development result of E-SIP is in terms of login page for users in three levels. The first level is Super Admin which is responsible to input all databases needed for E-SIP. The second level is Department Admin, which is responsible to arrange the individual schedule of departments. The third level is Faculty Admin, which only able to see the schedule arranged by Department Admin. The similarity of all levels is to print and see the schedule. The advantage of E-SIP is that the scheduling system is able to be controlled by online and performed simultaneously at one time as well as to check overlapping or nonautomatic schedules in the website. Besides, the disadvantage happens when there is a bug or an error resulting in that the system does not function properly and needs to be immediately resolved.
, Suguna Ramadass
Ingénierie des systèmes d information, Volume 26, pp 311-318;

Digital Technology is becoming increasingly essential to organizations. Related knowledge is important for a company to allow optimal use of its IT services. The use of Big Data is relatively new to this field. Handling Big data is not, at this stage, a problem for large business organizations in particular; it has also become a challenge for small and medium-sized businesses. Although Semantic Web analysis is largely focused on fundamental advances that are expected to make the Semantic Web a reality, there has not been much work done to demonstrate the feasibility and effect of the Semantic Web on business issues. The infrastructure of electronic information executives and business types has provided various enhancements for companies, such as the automated process of buying and selling products. Nevertheless, undertakings are checked for the multifaceted nature of the extension required to deal with an ever-increasing number of electronic details and procedures. This paper suggests a model with a neural network design and a word representation system named Word2Vec for analyzing retail environment. Firstly, Word2vec manages the text data and shows it as a function diagram and a feature map is given to the Convolution Neural Network (CNN) that extracts the features and classifies them. The IMDB dataset, the Cornell dataset, the Amazon Products Dataset and the Twitter dataset were analyzed in the proposed model. The proposed Convolution Neural Network Fisher Kernel (CNN-FK) model is compared with the existing SVM model for analyzing retail environment in semantic web mining. The new approach has increased efficiency when compared to existing models.
, Mandapati Sridhar
Ingénierie des systèmes d information, Volume 26, pp 329-335;

In Visual Cryptography Schemes (VCSs), for message n transparencies are generated, such that the original message is visible if any k of them are stacked. VCS especially for large values of k and n, the pixel expansion’s reduction and enhancement of the recovered images’ display quality continue to be critical issues. In addition to this, it is challenging to develop a practical and systematic approach to threshold VCSs. An optimization-based pixel-expansion-free threshold VCSs approach has been proposed for binary secret images’ encryption. Along with contrast, blackness is also treated as a performance metric for assessing the recovered images’ display quality. An ideally secure technique for a secret image’s protection through its partition into shadow images (known as shadows) is the Visual Secret Sharing (VSS) scheme. Acquirement of a smaller shadow size or a higher contrast is the VSS schemes’ latest focus. The white pixels’ frequency has been utilized to demonstrate the recovered image’s contrast in this work. While the Probabilistic VSS (ProbVSS) scheme is non-expansible, it can also be readily deployed depending upon the traditional VSS scheme. Initially, this work has defined the problem as a mathematical optimization model such that, while contingent on blackness and density-balance constraints, there is the maximization of the recovered images’ contrast. Afterward, an algorithm dependent on the Tabu Search (TS) is devised in this work for this problem’s resolution. Multiple complicated combinatorial problems have been successfully resolved with the powerful TS algorithm. Moreover, this work has attempted to bolster the contrast through the density-balance constraint’s slight relaxation. Compared to the older techniques, the proposed optimization-based approach is superior regarding the recovered images’ display quality and the pixel expansion factor from the experimental outcomes.
, Aroul Canessane Ramalingam
Ingénierie des systèmes d information, Volume 26, pp 303-310;

Traffic classification is very important field of computer science as it provides network management information. Classification of traffic become complicated due to emerging technologies and applications. It is used for Quality of Service (QoS) provisioning, security and detecting intrusion in a system. In the past used of port, inspecting packet, and machine learning algorithms have been used widely, but due to the sudden changes in the traffic, their accuracy was diminished. In this paper a Multi-Layer Perceptron model with 2 hidden layers is proposed for traffic classification and target traffic classify into different categories. The experimental results indicate that proposed classifier efficiently classifies traffic and achieves 99.28% accuracy without feature engineering.
, Abdallah Khababa
Ingénierie des systèmes d information, Volume 26, pp 295-302;

The interconnection of medical devices is emerging as a new requirement in modern medicine. The final goal of connecting heterogeneous medical devices in a wider network of computational servers is to monitor and improve patient safety, where it also constitutes a major goal in the Integrated Clinical Environment (ICE) framework. The heterogeneity of medical devices provided by different suppliers is a key challenge in ICE-based systems, where interoperability and data communication across devices is still under study and specification. ICE aims to create a standard interface that covers medical devices heterogeneity, hence, achieving interoperability in a safe way. It focuses on defining an interoperable bus between the patient, medical devices, software applications, and the clinician. Given the lack of realization of ICE standard, this paper presents a component-based framework for making ICE usable for medical applications. This work illustrates the component model in detail and validates it with a prototype implementation that focuses on the integration of heterogeneous medical devices as the most relevant requirements faced by ICE.
Nagaraju Devarakonda, Dasari Kavitha, Raviteja Kamarajugadda
Ingénierie des systèmes d information, Volume 26, pp 285-293;

In recent days many people are working on twitter data as the tweets are easily available and also provide reliable data. Collecting and processing these tweets produces promising and accurate results in solving many real world problems. Common problem faced by most of the people is traffic congestion. Traffic congestion results in traffic jams, mental and physical health disturbance. So to avoid this, our paper tried to show the methodology which can bring out promising results. In this paper for processing the tweet data we have used the common approach of Term Frequency-Inverse Document Frequency (TF-IDF) and discussed the application of brainstorming optimization algorithm (BSO) to avoid traffic congestion. We have also introduced the density peak clustering (DPC) to train the brain storming optimization technique. This paper has shown the modified BSO and DPC on the tweets to bring out the results which show traffic conditions at various places. We have justified our work by conducting the experiment.
, Vasanthi Varadharajan
Ingénierie des systèmes d information, Volume 26, pp 319-327;

With the pervasive usage of sensing systems and IoT things, the importance of security has increased. Attempts towards breaching IoT security systems by attackers are on upsurge. Many intrusions in embedded systems, sensing equipment and IoT things have occurred in the past. Though there are cyber security tools like Antivirus, Intrusion detection and prevention systems available for securing the digital devices and its networks. However, a forensic methodology to be followed for the analysis and investigation to detect origin cause of network incidents is lacking. This paper derives a comprehensive preventive cyber forensic process model with honeypots for the digital IoT investigation process which is formal, that can assist in the court of law in defining the reliability of the investigative process. One year data of various attacks to the IoT network has been recorded by the honeypots for this study. The newly derived model HIM has been validated using various methods and instead of converging on a particular aspect of investigation, it details the entire lifecycle of IoT forensic investigation. The model is targeted to address the forensic analysts’ requirements and the need of legal fraternity for a forensic model. The process model follows a preventive method which reduce further attacks on network.
Nurul Najihah A’Bas, , Mohamad Lutfi Dolhalit, Wan Sazli Nasaruddin Saifudin, Nazreen Abdullasim, Shahril Parumo, Raja Norliza Raja Omar, Siti Zakiah Md Khair, Khavigpriyaa Kalaichelvam, Syazwan Izzat Noor Izhar
Ingénierie des systèmes d information, Volume 26, pp 255-264;

Back to Top Top